Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add lihtness/gnomon-mcp --skill gnomongit clone --depth 1 https://github.com/lihtness/gnomon-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/lihtness/gnomon-mcp/gnomon)<a href="https://agentmods.dev/skills/lihtness/gnomon-mcp/gnomon"><img src="https://agentmods.dev/badge/skills/lihtness/gnomon-mcp/gnomon/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lihtness/gnomon-mcp/gnomon"><img src="https://agentmods.dev/badge/skills/lihtness/gnomon-mcp/gnomon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00058 | $0.01082 |
| Opus 5.5 | $0.00023 | $0.00433 |
| Sonnet 5.5 | $0.00012 | $0.00216 |
| Haiku 4.5 | $0.00006 | $0.00108 |
Grade A, and why
gnomon scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gnomon
gnomon-mcp exposes four MCP tools so the model computes deterministically instead of guessing.
Reach for gnomon whenever the answer involves
- The current date or time. Your training cutoff is not today. Call
now. - Elapsed time / time-until / time-since. Call
calendarwithdiff,until, orsince. - Date arithmetic (adding days/weeks/months/years, weekday lookups, business days, formatting). Call
calendar. - Natural-language dates ("next thursday", "in 3 hours", "last friday"). Call
calendarwithparse. - Arithmetic that matters — anything past trivial mental math: decimals, percentages, sums over many items, averages, statistics. Call
calc. - Unit conversion — metric/imperial, temperature, bytes, time durations. Call
calc_convert. Never eyeball.
The four tools
now(tz?) — current moment, rich dict
One call returns ISO, date, time, weekday, day_of_year, week_of_year (ISO), quarter, fiscal year (US gov), is_weekend, and more. Optional IANA timezone (defaults to UTC).
now() → UTC snapshot
now("America/Los_Angeles") → in a specific tz
calendar(ops) — batch date operations
Pass a list of {"op": NAME, ...args} dicts, get a list back in order. Use this for table-row workloads — one tool call covers a whole column.
calendar([
{"op": "until", "target": "2026-12-31", "unit": "days"},
{"op": "since", "source": "2026-01-01", "unit": "days"},
{"op": "diff", "start": "2026-01-01", "end": "2026-12-31", "unit": "days"},
{"op": "add", "date": "2026-05-25", "n": 1, "unit": "months"},
{"op": "weekday", "date": "2026-05-25"},
{"op": "business_days", "start": "2026-05-01", "end": "2026-06-01"},
{"op": "parse", "natural": "next thursday", "tz": "America/Los_Angeles"},
{"op": "format", "date": "2026-05-25", "fmt": "%A, %B %d %Y"},
])
Units for diff/until/since: seconds, minutes, hours, days, weeks.
Units for add: above plus months, years (calendar-aware via relativedelta).
business_days counts Mon-Fri (start inclusive, end exclusive); doesn't yet know holidays.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 80 lines · 58 tokens per session scan A 877a8a99e729
gnomon is a skill published in the GitHub repository lihtness/gnomon-mcp (1 stars, last pushed 5mo ago), licensed MIT. It adds 58 tokens to every session and 1,082 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
send-email
Compose and send a one-off email to a named recipient via Resend - written in the operator's voice, then sent in-run through the shared send caps with an operator audit copy.
caveman-help
Quick-reference card for all caveman modes, skills, and commands. One-shot display, not a persistent mode. Trigger: /caveman-help, "caveman help", "what caveman commands", "how do I use caveman".
get-started
First-run setup for the Aeon plugin. Checks the connection to the user's Aeon agent, shows what it can do, and runs one skill so the user sees it work. Use right after the plugin is installed, or when the user asks how to get started with Aeon.
skill-factory
A workflow that examines completed session work and turns reusable patterns into Claude Code skills.
session-wrap
Use when wrapping up a session before ending. 4 parallel subagents detect doc updates, repeated patterns, learning points, and follow-ups, then a verifier deduplicates and presents choices. Triggers on /session-wrap, session wrap, session cleanup, end of session.
toolbox
Pre/post dev toolbox — named bundles of skills/agents loaded before development work and councils of experts invoked after. Run /toolbox or the toolbox.py CLI to list, activate, initialize, export, import, and validate toolboxes. Invoke at the start or end of a dev session, when setting up a new repo, or when sharing…